机器学习和随机算法Large-scale Machine Learning and Stochastic Algorithms |
|
课程网址: | http://videolectures.net/opt08_bottou_lsml/ |
主讲教师: | Léon Bottou |
开课单位: | 脸书公司 |
开课时间: | 2008-10-20 |
课程语种: | 英语 |
中文简介: | 该演示强调机器学习和传统优化方法之间的重要差异,并提出一些解决方案。第一部分讨论了两种渐近性质的相互作用:统计量和优化算法的相互作用。不太可能的优化算法,如随机梯度,表现出惊人的大规模机器学习问题的性能。第二部分展示了这种性能的深层原因如何表明理论上的可能性通过一次通过数据来学习大规模问题。将讨论实用算法:各种二阶随机梯度,平均方法,数据再处理的双重方法...... |
课程简介: | The presentation stresses important differences between machine learning and conventional optimisation approaches and proposes some solutions. The first part discusses the the interaction of two kind of asympotic properties: those of the statistics and those of optimization algorithm. Unlikely optimization algorithm such as stochastic gradient show amazing performance for large-scale machine learning problems. The second part shows how the deeper causes of this performance suggests the theoretical possibility learn large-scale problems with a single pass over the data. Practical algorithms will be discussed: various second order stochastic gradients, averaging methods, dual methods with data reprocessing... |
关 键 词: | 机器学习; 随机梯度; 二阶随机梯度 |
课程来源: | 视频讲座网 |
最后编审: | 2020-01-13:chenxin |
阅读次数: | 46 |